Geodesic fuzzy rough sets based on overlap functions and its applications in feature extraction

As one of the current hot topics, feature extraction techniques have been widely studied, with the aim of selecting important and distinctive feature subsets from the original data to realize data dimensionality reduction. However, current feature extraction techniques lack the consideration of complex manifold structures in high-dimensional data, thus failing to fully exploit the information value of the data. To solve this problem, we introduce overlap functions (an emerging class of commonly used information aggregation functions with a wide range of applications) into the geodesic fuzzy rough set model and propose a new model named OKGFRS, which can effectively capture the potential manifold structures in high-dimensional data and deal with the imbalanced data. On this basis, we design a new discriminative feature extraction algorithm to improve the discriminative performance of feature extraction and to solve the problems such as poor distinguishing ability of features. After experimental verification, the algorithm demonstrates good classification performance.